This paper presents an hybrid approach to control a simulated AGV (Autonomous Guided Vehicle) for an automotive industry. The proposed approach integrates planning (and re-planning) based on the A* algorithm, with fuzzy obstacle avoidance, in order to avoid unknown or mobile obstacles present in the path of the AGV. The approach is evaluated in a simulated environment, and in the near future the approach is to be deployed in a real fabrication line.

This work presents the use of multiple mobile robots to perform a common transportation task. The main objective is to perform a navigation with a shared cargo, which allows the transport of objects with high payload or high sizes. Two robots are virtually linked through two Fuzzy controllers, one to control distance and another for orientation. A depth camera on the trailer's robot is used to measure the distance and orientation of the leader robot. The proposed approach is experimentally validated with two standard Pioneer mobile robots that collaboratively carry a large box.

Set plays are predefined collaborative coordinate actions that players from any sport can use to gain advantage over its adversaries. Recently, a complete framework for creation and execution of this kind of coordinate behavior by teams composed of multiple independent agents was launched as free software (the Set play Framework). In this paper, an approach based on Reinforcement Learning(RL) is proposed, that allows the use of experience to devise the better course of action in set plays with multiple choices. Simulations results show that the proposed approach allows a team of simulated agents to improve its performance against a known adversary team, achieving better results than previously proposed approaches using RL.